Run 4. Outer Step 29. Inner Step 37.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539642,
-    5539645,
-    5539647,
-    5539649,
-    5539651,
-    5539653,
-    5539656,
-    5539658,
-    5539661
+    5539664,
+    5539667,
+    5539669,
+    5539670,
+    5539673
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6dd28d23ed52f65373b6d5a99142a95762ad31a2889f9c7ecdbb2eb8a67f71f
+oid sha256:987c1a50f273fe733f005e73f4f286f8a8dc49bb8906ddd131e7f640fa178c16
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b3215798ce8c9f975edd657f70dd48a806ee08fa177546c94e35a95550f64d
+oid sha256:7fdc5f2ceae5b4d2537d25128999e6ef9f7f5ca34f675a3c4f1806b1c59316a9
 size 4040701744